Among　various　kinds　of　image　denoising　methods,　the　Perona–Malik　model　is　a　representative　Partial　Differential　Equation　(PDE)　based　algorithm　which　effectively　removes　the　noise　as　well　as　having　edge　enhancement　simultaneously　through　anisotropic　diffusion　controlled　by　the　diffusion　coefficient.　However,　Partial　Differential　Equations　(PDE)　is　good　at　removeling　Gaussian　noises,　but　it　is　not　an　ideal　method　to　deal　with　salt-and-pepper　noise.　To　realize　less　diffusion　in　the　texture　region　and　more　smooth　in　flat　region　while　implementing　image　denoising,　this　paper　propose　an　improved　Perona–　Malik　model　based　on　new　diffusion　function　which　change　with　the　number　of　iterations.　The　improved　algorithm　is　applied　on　numerical　simulation　and　practical　images,　and　the　quantitative　analyzing　results　prove　that　the　modified　anisotropic　diffusion　model　can　preserve　textures　effectively　while　ruling　out　the　noise,　meanwhile,　the　PSNR　are　increased　obviously.　©　Springer　International　Publishing　AG　2017.